Final Image Resolution Research Articles

FuBay: An Integrated Fusion Framework for Hyperspectral Super-Resolution Based on Bayesian Tensor Ring.

Fusion with corresponding finer-resolution images has been a promising way to enhance hyperspectral images (HSIs) spatially. Recently, low-rank tensor-based methods have shown advantages compared with other kind of ones. However, these current methods either relent to blind manual selection of latent tensor rank, whereas the prior knowledge about tensor rank is surprisingly limited, or resort to regularization to make the role of low rankness without exploration on the underlying low-dimensional factors, both of which are leaving the computational burden of parameter tuning. To address that, a novel Bayesian sparse learning-based tensor ring (TR) fusion model is proposed, named as FuBay. Through specifying hierarchical sprasity-inducing prior distribution, the proposed method becomes the first fully Bayesian probabilistic tensor framework for hyperspectral fusion. With the relationship between component sparseness and the corresponding hyperprior parameter being well studied, a component pruning part is established to asymptotically approaching true latent rank. Furthermore, a variational inference (VI)-based algorithm is derived to learn the posterior of TR factors, circumventing nonconvex optimization that bothers the most tensor decomposition-based fusion methods. As a Bayesian learning methods, our model is characterized to be parameter tuning-free. Finally, extensive experiments demonstrate its superior performance when compared with state-of-the-art methods.

Incorporating convolutional and transformer architectures to enhance semantic segmentation of fine-resolution urban images

ABSTRACT Though convolutional neural networks (CNN) exhibit promise in image semantic segmentation, they have limitations in capturing global context information, resulting in inaccuracies in segmenting small object features and object boundaries. This study introduces a hybrid network, ICTANet, which incorporate convolutional and Transformer architectures to improve the segmentation performance of fine-resolution remote sensing urban imagery. The ICTANet model is essentially a Transformer-based encoder-decoder structure. The dual-encoder architecture, which combines CNN and Swin Transformer modules, is designed to extract both global and local detail information. The feature information at various stages is collected by the Feature Extraction and Fusion modules (FEF), enabling multi-scale contextual information fusion. In addition, an Auxiliary Boundary Detection (ABD) module is introduced at the end of the decoder to enhance the model’s ability to capture object boundary information. Numerous ablation experiments have been conducted to demonstrate the efficacy of various components within the network. The testing results have proven that the proposed model can achieve satisfactory performance on the ISPRS Vaihingen and Potsdam dataset, with overall accuracies of 91.9% and 92.0%, respectively. Simultaneously, the proposed model is also compared to the current state-of-the-art methods, exhibiting competitive performance, particularly in the segmentation of diminutive objects like cars and trees.

High-resolution landslide mapping and susceptibility assessment: Landslide temporal variations and vegetation recovery

In mountainous terrains, the frequent landslides and their associated impacts on human lives and the economy is increasing globally. Development of landslide inventory and afterward landslide susceptibility mapping are the main prerequisites for implementing landslide mitigation measures and protection in mountainous regions. The 2005 Kashmir earthquake induced different small and large landslides and some were active for the long term. So far many studies have used medium and high-resolution data to develop landslide inventory. This study aims to develop a 1st detailed, comprehensive and accurate landslide inventory using a very high-resolution image using a semi-automatic technique. The precise landslide inventory is employed to develop an accurate and comprehensive landslide susceptibility map considering the landslide inventory data using a logistic regression training model. Furthermore, the landslide’s temporal recovery from the earthquake and its reactivation due to rainfall in spare vegetation areas have been evaluated. Fine-resolution satellite images of Worldview-2 are applied to develop a detailed landslide inventory using a Support Vector Machine (SVM) classifier. A total of 63,630 landslides were identified using a semi-automatic technique within a study area of 265 km2. From regression modeling, the results show that geology, topography, and road networks have a significant impact on the spatial distribution of landslides. Model performance was evaluated based on the testing data, the model gives an AUC of 0.93 and the kappa value of 0.9353. The spatiotemporal NDVI has been assessed to identify the landslide recovery and its reactivation due to extreme rainfall. The results show that 72.1 % of the landslides occurred in Muzaffarabad formation in the study area. The developed landslide susceptibility map can be further used for land-use planning and implementing mitigation measures for the safety of roads and other infrastructure in the area.

Intensity correlation imaging design for geostationary satellite inspection

Recent advances in the reduction of the integration time required of intensity correlation imaging (ICI) have opened the possibility for significant improvements in astronomical imaging. This paper discusses the application of ICI to the fine-resolution imaging of geostationary satellites conducted by ground-based observatories.

Bifunctional octadentate pseudopeptides as Zirconium-89 chelators for immuno-PET applications

BackgroundPositron emission tomography (PET) is a highly sensitive method that provides fine resolution images, useful in the field of clinical diagnostics. In this context, Zirconium-89 (89Zr)-based imaging agents have represented a great challenge in molecular imaging with immuno-PET, which employs antibodies (mAbs) as biological vectors. Indeed, immuno-PET requires radionuclides that can be attached to the mAb to provide stable in vivo conjugates, and for this purpose, the radioactive element should have a decay half-life compatible with the time needed for the biodistribution of the immunoglobulin. In this regard, 89Zr is an ideal radioisotope for immuno-PET because its half-life perfectly matches the in vivo pharmacokinetics of mAbs.ResultsThe main objective of this work was the design and synthesis of a series of bifunctional octadentate pseudopeptides able to generate stable 89Zr complexes. To achieve this, here we investigated hydroxamate, N-methylhydroxamate and catecholate chelating moieties in complexing radioactive zirconium. N-methylhydroxamate proved to be the most effective 89Zr-chelating group. Furthermore, the increased flexibility and hydrophilicity obtained by using polyoxyethylene groups spacing the hydroxamate units led to chelators capable of rapidly forming (15 min) stable and water-soluble complexes with 89Zr under mild reaction conditions (aqueous environment, room temperature, and physiological pH) that are mandatory for complexation reactions involving biomolecules. Additionally, we report challenge experiments with the competitor ligand EDTA and metal ions such as Fe3+, Zn2+ and Cu2+. In all examined conditions, the chelators demonstrated stability against transmetallation. Finally, a maleimide moiety was introduced to apply one of the most promising ligands in bioconjugation reactions through Thiol-Michael chemistry.ConclusionCombining solid phase and solution synthesis techniques, we identified novel 89Zr-chelating molecules with a peptide scaffold. The adopted chemical design allowed modulation of molecular flexibility, hydrophilicity, as well as the decoration with different zirconium chelating groups. Best results in terms of 89Zr-chelating properties were achieved with the N-methyl hydroxamate moiety. The Zirconium complexes obtained with the most effective compounds were water-soluble, stable to transmetallation, and resistant to peptidases for at least 6 days. Further studies are needed to assess the potential of this novel class of molecules as Zirconium-chelating agents for in vivo applications.

Improving spatiotemporal image fusion incorporating unmixing step by considering the point spread function effect

ABSTRACT In this paper, an improving spatiotemporal image fusion (STIF) incorporating unmixing step by considering the point spread function (PSF) effect model (CPSF) is proposed to address the problem that unmixing accuracy in STIF models incorporating unmixing step is vulnerable to the PSF effect. First, an unsupervised clustering algorithm is used to cluster the fine image at previous date into a land cover map, and the coarse class fraction matrix is generated from this land cover map. Second, the fine class fraction matrix uncontaminated by the PSF effect is calculated by upsampling the coarse class fraction matrix using the Area-to-Point Kriging (ATPK) method under the PSF constraint. Third, this fine class fraction matrix is convolved with the ideal square wave filter to downsample, and then normalized to obtain the coarse class fraction matrix without the influence of the PSF effect. Finally, the CPSF-processed class fraction matrix is used to replace the original one in the following unmixing and prediction process to generate the fine resolution image at the prediction date. Experiments on two remote sensing data sets show that the proposed method can effectively improve the accuracy of spatiotemporal image fusion methods incorporating unmixing step.

Relationship between monthly surface water derived from Sentinel-2 imagery and meteorological data (precipitation and evaporation) at Baghdad, Iraq

ABSTRACT This study was carried out using two main monthly datasets: satellite images and some meteorological parameters (like precipitation and evaporation) for 2 years (2018 and 2021). Using the fine spatial resolution images acquired from Sentinel-2, digital maps of surface water areas were produced by calculating the Modified Normalized Difference Water Index for all months in QGIS and then classifying them into two main categories (water and non-water bodies). The results show that the largest areas were in January 2021 (77.2 km2) and 40.7 km2 in November 2018, while the lowest (18.7 km2) were in June 2021 and July 2018. Monthly mean values of cumulative precipitation and evaporation were used to find their relationships with surface water areas. The results show that the year 2021 was a severe dry year, whereas the lowest precipitation (25 mm) in that year was associated with higher evaporation losses (3,021.8 mm) during this year. When combined with surface water areas and meteorological parameters, a non-linear relationship between water areas and evaporation was found for both years, and a linear relationship between precipitation and water areas for the wet year of 2018.

Canopy-Level Spectral Variation and Classification of Diverse Crop Species with Fine Spatial Resolution Imaging Spectroscopy

Canopy-Level Spectral Variation and Classification of Diverse Crop Species with Fine Spatial Resolution Imaging Spectroscopy

Automatic Speckle Noise Reduction in SAR Imagery Using Optimized Kernel Support Vector Machine

Speckle noise (SN) is one of the major types of noise that frequently occurs in different coherent imaging systems such as medical imaging, Synthetic Aperture Radar (SAR) and active Radar images. SAR is a powerful imaging technology that generates fine-resolution images and monitors the earth’s surface in order to identify its physical properties. The satellite images captured by SAR are mainly affected by SN, which reduces the quality of images and complicates the image representation. Therefore, removing SN from SAR images is one of the major challenges and needs significant attention. The proposed study introduces an optimal Machine Learning (ML) classifier named Kernel Support Vector Machine-Improved Aquila Optimization (KSVM-IAO) for reducing SN in SAR images. This study uses a two-step process called filtering and enhanced despeckling to minimize the consequence of speckle suppression. In the first step, different imaging filters, namely Improved Lee Filter (ILF), Improved Frost Filter (IFF), Improved Kuan Filter (IKF) and Improved Boxcar Filter (IBF), are utilized to remove the SN in SAR images. Next, the denoised image is fed to the second stage, which makes use of an optimized KSVM-IAO classifier to obtain an enhanced despeckle image. The hyperparameters of KSVM are tuned using the IAO algorithm, which reduces overfitting issues and increases accuracy. MATLAB is the simulation tool used for the analysis of SAR images. The simulation outcomes reveal that the proposed KSVM-IAO method obtained excellent SN removal while preserving the edges and fine details with low computational complexity.

Convolutional neural networks for compressible turbulent flow reconstruction

This paper investigates deep learning methods in the framework of convolutional neural networks for reconstructing compressible turbulent flow fields. The aim is to develop methods capable of up-scaling coarse turbulent data into fine-resolution images. The method is based on a parallel computational framework that accepts five image sets of various resolutions, trained to correspond to the respective fine resolution. The network architecture mainly consists of convolutional layers, constructing an encoder/decoder network. Based on the U-Net scheme, three different implementations are presented, with residual and skip connections. The methods are implemented in a supersonic shock-boundary-layer interaction problem. The results suggest that simple networks perform better when trained on limited data, and this can be a practical and fast solution when dealing with turbulent flow data, where the computational burden is most of the time difficult to decrease. In such a way, a coarse simulation grid can be upscaled to a fine grid.

Adaptive Technique for Contrast Enhancement of Leading Vehicle Tracks

During movement in various unpaved terrain conditions, the track impressions left over by the leading vehicles provide guiding and safe routes in the area. The delineation of these tracks captured by the images can extend immense support for guidance in real time. These tracks that look like edges in coarse-resolution images take the shape of elongated areas in fine-resolution images. In such a scenario, the high pass and edge detection filters give limited information to delineate these tracks passing through different surroundings. However, the distinct texture of these tracks assists in the delineation of these tracks from their surroundings. Gray level co-occurrence matrix (GLCM) representing the spatial relation of pixels is employed here to define the texture. The authors investigated the influence of different resolutions on the distinguishability of these tracks. The study revealed that texture plays an increasing role in distinguishing objects as the image resolution improves. The texture analysis extended to investigate the track impressions left over by the leading vehicle brings out an ample scope in delineating these tracks. The measures could improve the track contrast even better than conventional techniques. To select the most optimal contrast enhancement measure in a given scenario, authors proposed a quantified measure of track index. An investigation is made on the difference-based track index (TI) representing the mean contrast value of the track vis-à-vis off-track areas. The results show an increase in the quantified contrast from 7.83 per cent to 29.06 per cent. The proposed technique highlights the image with the highest track contrast in a given scenario. The study can lead to onboard decision-making for the rut following vehicles moving in low-contrast terrain.

A planar dimension measurement optimization method with metric information compensation

Visual dimension measurement is commonly required in industrial detection. However, monocular vision measurements have a low accuracy with large field of view (FOV), while multi-vision measurement involves multi-source information fusion and incurs a large computation overhead. Hence, we propose a planar dimension measurement optimization method with metric information compensation (PMOM). This method constructs a linear representation model of pixel metric information using images at different heights along the camera’s optical axis; designs a multi-resolution multi-dimensional key point mapping mechanism (KPM) to realize the projection from a coarse resolution image point to a fine resolution image block and the secondary optimization of measurement results. By utilizing pixel-level and subpixel-level object extraction algorithms for both coarse resolution and fine resolution image blocks, the algorithm’s complexity and data processing requirements are notably reduced. The paper includes a theoretical proof of the method’s effectiveness, shown by analyzing the measurement errors of different resolution images. Comparative experiments on the measurement of spacing between planar patterns and workpiece machining accuracy validate the method meeting the requirements of industrial high-precision with a large FOV and low computational overhead.

Spatial enhanced spatiotemporal reflectance fusion model for heterogeneous regions with land cover change

Numerous spatiotemporal fusion models have been developed to fuse dense time-series data with a high spatial resolution for monitoring land surface dynamics. Nonetheless, enhancing spatial details of fused images, eliminating the obvious ‘plaque’ phenomenon and image blurring in fused images, and developing relatively simple and 1 easy-to-implement algorithms remain a challenge for spatiotemporal fusion algorithms. Therefore, this paper presents a newly proposed spatial enhanced spatiotemporal reflectance fusion model (SE-STRFM) for image fusions in heterogeneous regions with land cover change. The SE-STRFM model predicts temporal changes of reflectance in sub-pixel details based on the spectral unmixing theory, and allocates reflectance changes caused by abrupt land cover change in fine-resolution images with a relatively simple algorithm and easy implementation. SE-STRFM only needs one pair of input data, comprising one fine-resolution image and one coarse-resolution image, to achieve high-precision reflectance prediction with spatial details. To verify the reliability and applicability of the SE-STRFM, we use Landsat image and simulated MODIS-like image to fuse high spatial and temporal resolution images and select two study areas with heterogeneous landscape and land cover type change for fusion experiments and accuracy evaluation. The results show that the images fused by SE-STRFM have clearer spatial details and a more accurate spectral distribution compared with those fused by the most widely used STARFM, ESTARFM and FSDAF. In two study areas with heterogeneous landscape and land cover type change, compared with STARFM, ESTARFM and FSDAF, the RMSE of SE-STRFM is 10.52%, 28.39% and 6.58% lower on average, respectively; r is 3.67%, 10.33% and 1.65% higher on average, respectively; AAD is 9.05%, 24.58% and 7.29% lower on average, respectively; and SSIM is 3.16%, 10.16% and 1.92% higher on average, respectively. SE-STRFM can accurately capture temporal changes with spatial details and effectively predict abrupt land-cover changes.

Greening residential quarters in China: What are the roles of urban form, socioeconomic factors, and biophysical context?

Residential greenspace has great intracity variations. Its driving factors have been widely investigated in Western countries (e.g., in Europe and North America), where residential areas are mostly privately owned, but few studies have examined the determinants of residential greenspace in China, where land is owned by the government. Taking the subtropical city of Changsha, China, as an example, this study mapped the percent green cover (PGC) in residential quarters with a fine-resolution satellite image. We also investigated its driving factors measured from multisource geospatial data. The results show that (1) the PGC in the residential quarters showed great spatial variation, with an average of 36.6% (0–85.7%) and a standard deviation of 18.3%. (2) Urban form, biophysical context, and socioeconomic factors together explained 49.18% of the variation in the PGC, and they independently explained 22.87%, 11.17%, and 2.31% of the variation, respectively. (3) Residential quarter size, PGC in the surrounding buffer zone, residential quarter age, housing value, and population density significantly and positively impact the PGC, while percent building cover, floor area ratio, and distance to city center had significant negative impacts. The strongest positive and negative impacts came from PGC in the surrounding buffer zone and percent building cover, respectively. Socioeconomic factors, the dominant driving factors in Western countries, show little impact on residential PGC. These findings expand our understanding of the intracity variation in greenspace coverage and the driving factors, which sheds light on the effective planning and management of urban greenspaces in China.

Detecting and Predicting Archaeological Sites Using Remote Sensing and Machine Learning—Application to the Saruq Al-Hadid Site, Dubai, UAE

In this paper, the feasibility of satellite remote sensing in detecting and predicting locations of buried objects in the archaeological site of Saruq Al-Hadid, United Arab Emirates (UAE) was investigated. Satellite-borne synthetic aperture radar (SAR) is proposed as the main technology for this initial investigation. In fact, SAR is the only satellite-based technology able to detect buried artefacts from space, and it is expected that fine-resolution images of ALOS/PALSAR-2 (L-band SAR) would be able to detect large features (>1 m) that might be buried in the subsurface (<2 m) under optimum conditions, i.e., dry and bare soil. SAR data were complemented with very high-resolution Worldview-3 multispectral images (0.31 m panchromatic, 1.24 m VNIR) to obtain a visual assessment of the study area and its land cover features. An integrated approach, featuring the application of advanced image processing techniques and geospatial analysis using machine learning, was adopted to characterise the site while automating the process and investigating its applicability. Results from SAR feature extraction and geospatial analyses showed detection of the areas on the site that were already under excavation and predicted new, hitherto unexplored archaeological areas. The validation of these results was performed using previous archaeological works as well as geological and geomorphological field surveys. The modelling and prediction accuracies are expected to improve with the insertion of a neural network and backpropagation algorithms based on the performed cluster groups following more recent field surveys. The validated results can provide guidance for future on-site archaeological work. The pilot process developed in this work can therefore be applied to similar arid environments for the detection of archaeological features and guidance of on-site investigations.

Evaluating resampled and fused Sentinel-2 data and machine-learning algorithms for mangrove mapping in the northern coast of Qeshm island, Iran

Mangrove forests, as an essential component of the coastal zones in tropical and subtropical areas, provide a wide range of goods and ecosystem services that play a vital role in ecology. Mangroves are globally threatened, disappearing, and degraded. Consequently, knowledge on mangroves distribution and change is important for effective conservation and making protection policies. Developing remote sensing data and classification methods have proven to be suitable tools for mapping mangrove forests over a regional scale. Here, we scrutinized and compared the performance of pixel-based and object-based methods under Support Vector Machine (SVM) and Random Forest (RF) algorithms in mapping a mangrove ecosystem into four main classes (Mangrove tree, mudflat, water, and sand spit) using resampled and fused Sentinel-2 images. Additionally, landscape metrics were used to identify the differences between spatial patterns obtained from different classification methods. Results showed that pixel-based classifications were influenced heavily by the effect of salt and pepper noise, whereas in object-based classifications, boundaries of land use land cover (LULC) polygons were smoother and visually more appealing. Object-based classifications, with an excellent level of kappa, distinguished mudflat and sand spit from each other and from mangrove better than the pixel-based classifications which obtained a fair-to-good level of kappa. RF and SVM performed differently under comparable circumstances. The results of landscape metrics comparison presented that the classification methods can be affected on quantifying area and size metrics. Although the results supported the idea that fused Sentinel images may provide better results in mangrove LULC classification, further research needs to develop and evaluate various image fusion approaches to make use of all Sentinel’s fine resolution images. Our results on the mapping of mangrove ecosystems can contribute to the improvement of management and conservation strategies for these ecosystems being impacted by human activities.

Mapping the spatial distribution of alpine shrubs on the Qinghai–Tibet Plateau using Sentinel-2 images

ABSTRACT Shrubs are typical vegetation on the Qinghai – Tibet Plateau, and their spatial distribution pattern is crucial for understanding the regional ecological environment. Existing global land cover products cannot represent shrubs well in this area, and the relationship between shrubs and the corresponding environmental factors is still unclear. In this study, using the Dogxung Zangbo River Basin as an example, Sentinel-2 images were applied to estimate the regional shrub fraction image, using the random forest regression model trained with samples generated from fine-resolution Jilin-1 images. The estimated shrub fraction image was further analysed using an elevation dataset to explore the impact of topography on the spatial distribution of shrubs. The results showed that using Sentinel-2 images acquired in both plant growing and non-growing seasons can better distinguish shrubs from grass than using only one season of data, and the coefficient of determination and root-mean-square error derived from this model were 0.821 and 0.087, respectively. The shrub distribution was strongly correlated with topography. In the study area, areas with a southeast or south orientation and large slope are more suitable for shrub growth.

Spectral variability in fine-scale drone-based imaging spectroscopy does not impede detection of target invasive plant species

Land managers are making concerted efforts to control the spread of invasive plants, a task that demands extensive ecosystem monitoring, for which unoccupied aerial vehicles (UAVs or drones) are becoming increasingly popular. The high spatial resolution of unoccupied aerial vehicles imagery may positively or negatively affect plant species differentiation, as reflectance spectra of pixels may be highly variable when finely resolved. We assessed this impact on detection of invasive plant species Ailanthus altissima (tree of heaven) and Elaeagnus umbellata (autumn olive) using fine-resolution images collected in northwestern Virginia in June 2020 by a unoccupied aerial vehicles with a Headwall Hyperspec visible and near-infrared hyperspectral imager. Though E. umbellata had greater intraspecific variability relative to interspecific variability over more wavelengths than A. altissima, the classification accuracy was greater for E. umbellata (95%) than for A. altissima (66%). This suggests that spectral differences between species of interest and others are not necessarily obscured by intraspecific variability. Therefore, the use of unoccupied aerial vehicles-based spectroscopy for species identification may overcome reflectance variability in fine resolution imagery.

Gap-Filling Sentinel-1 Offshore Wind Speed Image Time Series Using Multiple-Point Geostatistical Simulation and Reanalysis Data

Offshore wind is expected to play a key role in future energy systems. Wind energy resource studies often call for long-term and spatially consistent datasets to assess the wind potential. Despite the vast amount of available data sources, no current means can provide relevant sub-daily information at a fine spatial scale (~1 km). Synthetic aperture radar (SAR) delivers wind field estimates over the ocean at fine spatial resolution but suffers from partial coverage and irregular revisit times. Physical model outputs, which are the basis of reanalysis products, can be queried at any time step but lack fine-scale spatial variability. To combine the advantages of both, we use the framework of multiple-point geostatistics to realistically reconstruct wind speed patterns at time instances for which satellite information is absent. Synthetic fine-resolution wind speed images are generated conditioned to coregistered regional reanalysis information at a coarser scale. Available simultaneous data sources are used as training data to generate the synthetic image time series. The latter are then evaluated via cross validation and statistical comparison against reference satellite data. Multiple realizations are also generated to assess the uncertainty associated with the simulation outputs. Results show that the proposed methodology can realistically reproduce fine-scale spatiotemporal variability while honoring the wind speed patterns at the coarse scale and thus filling the satellite information gaps in space and time.

An enhanced spatiotemporal fusion model with degraded fine-resolution images via relativistic generative adversarial networks

Limited by the sensor technology and budget, spatiotemporal fusion (STF) of remote sensing images (RSIs) is an effective strategy to obtain products with dense time and high spatial resolution. The STF methods generally require at least three observed images, and the predicted results depend on the reference date. The lack of high-quality fine-resolution images in practice makes the STF model difficult to apply, and few models consider the bias caused by different sensors. To solve the above problems, an enhanced STF model with degraded fine-resolution images via relativistic generative adversarial networks is proposed, called EDRGAN-STF, which is an end-to-end network with all bands trained simultaneously. To reduce the bias caused by different sensors, a degraded resolution version of the Landsat image with an arbitrary date is introduced into the STF model. The inputs of EDRGAN-STF only contain a MODIS image of the predicted date, a reference Landsat image and degraded version with an arbitrary date. EDRGAN-STF consists of a generator and a relativistic average least squares discriminator (RaLSD). A dual-stream residual dense block is designed to fully obtain the local and global spatial details and low-frequency information in the generator. A multihierarchical feature fusion block is designed to fuse global information. A spectral-spatial attention mechanism is employed in the generator, which focuses on important spectral bands and spatial features and enhances the reconstruction of critical regions. A new composite loss function is introduced to better optimize the designed STF model. To verify the capability of the EDRGAN-STF, extensive experiments are conducted on two typical Landsat-MODIS datasets, and results illustrate that EDRGAN-STF improves the STF accuracy and has great prospects for practical applications. Key policy highlights: The proposed EDRGAN-STF improves spatiotemporal fusion accuracy and has great prospects for practical applications. A degraded resolution version of the Landsat image with an arbitrary date is introduced into the spatiotemporal fusion model. A dual-stream residual dense block is designed to fully obtain the local and global spatial details and low-frequency information. A spectral-spatial attention mechanism focuses on important spectral bands and spatial features and enhances the reconstruction of critical regions. A multihierarchical feature fusion block fuses global information and a new composite loss function is introduced to better optimize the model.